- Architecture DiagramGenerate architecture diagram with component relationship details from project analysismicrosoft/github-copilot-modernization26
- AssessmentRun application assessment for a single repositorymicrosoft/github-copilot-modernization26
- Building Java Knowledge GraphAnalyzes JVM projects (Java/Kotlin/Scala/Groovy) and generates knowledge graphs with tree-sitter parsing. Requires Python 3 on the host and a JVM project with Maven/Gradle/Ant/Ivy build files. Skips gracefully if either prerequisite is missing. Triggers when asked to "build knowledge graph", "analyze project structure", "parse Java codebase", or "generate dependency graph".microsoft/github-copilot-modernization26
- Business WorkflowsGenerate core business workflow documentation with sequence diagrammicrosoft/github-copilot-modernization26
- Clarifying ScenariosEvaluates whether a user's modernization/rewrite request provides enough scenario context to proceed (e.g., target component library, screenshots, design system for frontend; API contract policy, data migration strategy for backend). Produces a deterministic clarity score, asks the user for missing required fields via a structured form, and writes a canonical `clarification.md` artifact consumed by all downstream agents. Triggers: "clarification gate", "scenario clarification", "elicit missing cmicrosoft/github-copilot-modernization26
- Configuration InventoryGenerate comprehensive configuration and externalized settings inventorymicrosoft/github-copilot-modernization26
- Create Modernization PlanCreate a modernization plan to migrate the project to Azuremicrosoft/github-copilot-modernization26
- Creating Implementation PlanCreates an implementation plan AND task breakdown from a feature spec by consuming design artifacts. Produces plan.md with implementation steps, inline task list with full REQ traceability, and a Requirement Mapping table. This is the single skill for planning + decomposition. Triggers: "create implementation plan", "plan for implementation", "assemble implementation plan", "generate plan from spec", "break down tasks", "generate tasks from plan", "create implementation tasks", "decompose the plmicrosoft/github-copilot-modernization26
- Dag GenerationGenerate task DAGs for modernization projects — select fragments from task catalog, produce initial DAG (Stage 1), and execute/validate DAG from plan artifacts (Stage 2).microsoft/github-copilot-modernization26
- Data ArchitectureGenerate data architecture and persistence layer documentation with data model diagrammicrosoft/github-copilot-modernization26
- Dependency MapGenerate dependency map diagram from project build filesmicrosoft/github-copilot-modernization26
- Feature InventoryCatalogs existing features from a codebase (API endpoints, user flows, UI screens, observable behaviors) and generates structured feature specs with REQ-XXX IDs, user scenarios, and success criteria. Triggers: "inventory features", "catalog existing functionality", "list what the app does", "extract requirements from code", "generate feature specs from research", "write a spec", "create feature specification", "define requirements". NOT for: implementation planning (use creating-implementation-pmicrosoft/github-copilot-modernization26
- GuidelinesCollection of framework-to-framework migration rules and transformation patterns (e.g., Struts→Spring MVC, JSP→Thymeleaf, EJB→Spring Boot). Triggers: "check migration guidelines", "look up transformation rules", "find Struts-to-Spring patterns", "apply migration conventions", "conversion rules for X→Y". Also consumed automatically by breaking-down-tasks and implementing-code during migration workflows. NOT for: direct execution — other skills scan this directory.microsoft/github-copilot-modernization26
- Implementing CodeExecutes a batch of implementation tasks with TDD workflow, source-anchored rewrite for behavioral fidelity, guideline-based code transformation, and full requirement tracing. Returns a structured batch report. Triggers: "implement tasks", "execute the batch", "write code for these tasks", "implement with source anchoring", "run the implementation". NOT for: task generation (use breaking-down-tasks), implementation planning (use creating-implementation-plan).microsoft/github-copilot-modernization26
- List PlansDiscovers valid migration plans in the workspace and returns the selected plan path. A valid plan is a subdirectory of .github/modernize/ that contains plan.md AND tasks.json (tasks.json may be in the plan folder or in a .metadata subfolder). Handles 0, 1, or multiple plans and prompts the user when a choice is needed. Triggers: "list plans", "find plans", "select plan", "list-and-select-plan", "discover plans".microsoft/github-copilot-modernization26
- Modernization Integration TestsRun multi-layer integration tests for modernized Java applications. Supports 4 layers - Layer 1 (TestContainers), Layer 2 (Smoke Tests), Layer 3 (Azure Integration), Layer 4 (Behavioral Comparison). Java projects only - skip if source code is not Java. Triggers: "generate integration tests", "add integration tests", "create Layer 1 tests", "create Layer 2 tests" NOT for: unit tests, performance tests, load tests.microsoft/github-copilot-modernization26
- Project DecompositionSingle-source codebase decomposition: scans a project scope, builds the module dependency graph, counts LOC by language, computes skip patterns (caller-supplied ∪ .gitignore ∪ baseline), and (when grouping is required) produces topology groupings with L3 quality validation. One skill owns ProjectProfile JSON, grouping protocols, and quality gates. Triggers: "before generating a workflow plan", "before topology grouping", "project sizing", "LOC counting", "module grouping", "topology splitting rumicrosoft/github-copilot-modernization26
- Project ReconZero-dependency shell recon for any code repository — detect languages, count LOC, and report project scale. Pure POSIX find/wc or PowerShell, no Python or third-party tools required. Triggers: "how big is this project", "what languages", "project sizing", "repo recon", "LOC count", "scope check".microsoft/github-copilot-modernization26
- Quality GatesRuns quality gate validation at each workflow stage. Supports 4 gate types: spec-quality, spec-to-plan, plan-to-tasks, completeness. Produces gate pass/fail reports with actionable feedback. Triggers: "run quality gate", "validate spec quality", "spec quality", "plan coverage", "check plan coverage", "validate plan to tasks", "check task traceability", "verify task completeness", "run completeness review", "review implementation", "check plan traceability", "check coverage", "completeness qualitmicrosoft/github-copilot-modernization26
- Runtime ValidationRuntime validation for migrated applications — covers testing strategy (planning phase) and test execution (validation phase): startup verification, integration testing, and end-to-end flow validation. Use when: (1) designing test strategy during planning phase (teamlead reads Part 1) (2) verifying a migrated app starts and runs correctly (3) writing or executing integration / E2E tests (tester reads Part 2) (4) choosing test tooling and environment setup (5) producing structured test evidencmicrosoft/github-copilot-modernization26
- Setting Up ConstitutionCreates or updates the project constitution that defines migration principles, constraints, and conventions. Triggers: "set up constitution", "define migration principles", "create project rules", "establish conventions", "establish migration constitution". NOT for: implementation, implementation planning, task generation.microsoft/github-copilot-modernization26
- Sharing LearningsHow to record project learnings so that later-phase workers and future agent runs can consume them.microsoft/github-copilot-modernization26
- Spring Boot ScaffoldingReference guide for creating a new Spring Boot project during rewrite migration.microsoft/github-copilot-modernization26
- Team ChartersProvides role charters (mission, ownership, core principles, quality bar) for a multi-agent coding team. Each charter defines the role's mission, ownership scope, core principle (boundary constraints), and quality bar. Most roles also include communication rules. Consumed by the coordinator during task decomposition to assign work to the correct role. Triggers: "look up role charter", "what does the architect own", "check role boundaries", "find team roles", "which role handles X", "list agent cmicrosoft/github-copilot-modernization26
- Build HealthAnalyze VS Code rolling build health on Azure DevOps. Use when: the rolling build is red right now, you need a report for the last 100 builds, you need to identify the commit range that broke the build, you are on build champ duty, or you need a build health report.microsoft/vscode-team-kit24
- Council PlanMulti-model council planning for implementation and architecture decisions. Use when the user asks to 'plan with council', 'multi-model plan', 'get different perspectives on approach', 'council plan', or wants multiple models to independently propose plans for the same task. Also use when the user asks to 'debate approaches', 'compare strategies', or 'cross-plan'.microsoft/vscode-team-kit24
- Council ReviewMulti-model council review for diffs, pull requests, and risky changes. It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use whenever the user asks for a review, PR feedback, a bug hunt in recent edits, or wants multiple models to inspect the same change independently. Also use when the user asks to 'discuss findings', 'cross-review', or 'debate' review results betwmicrosoft/vscode-team-kit24
- Follow GoalGive the agent a durable objective with a verifiable stopping condition, then keep iterating across turns until that condition is met. Use when the user says 'set a goal', 'follow a goal', '/goal …', 'keep working until …', or asks for a long-running task with a clear end state (migrations, large refactors, retry-until-green loops, experiments).microsoft/vscode-team-kit24
- Foundry Nextgen FrontendBuild elegant frontend UIs following Microsoft Foundry's NextGen Design System using Vite + React + pnpm. Use when creating dashboards, agent builders, data grids, entity management interfaces, or any application matching Foundry's refined dark-themed aesthetic. Triggers on requests for Foundry-style UI, NextGen design system, Microsoft Foundry interfaces, or enterprise admin dashboards with data tables, detail panels, and charts.microsoft/copilot-sdk-samples24
- GoalSet, inspect, or control a durable goal — the agent keeps iterating across turns until the stop condition is met.microsoft/vscode-team-kit24
- Inbox Add ReactionAdd a reaction to a GitHub issue or pull requestmicrosoft/vscode-team-kit24
- Inbox Dismiss NotificationDismiss GitHub notificationmicrosoft/vscode-team-kit24
- Inbox Get Notification DetailsGet details of a specific GitHub notification threadmicrosoft/vscode-team-kit24
- Inbox Install Gh CliInstall the GitHub CLI (gh) if not already installedmicrosoft/vscode-team-kit24
- Inbox List NotificationsFetch GitHub notifications using the gh CLImicrosoft/vscode-team-kit24
- Inbox Manage SubscriptionManage subscription for a GitHub notification threadmicrosoft/vscode-team-kit24
- Inbox Mark All ReadMark all GitHub notifications as readmicrosoft/vscode-team-kit24
- Inbox MemoryRead and write agent storage — memory and rules with environment-aware fallbackmicrosoft/vscode-team-kit24
- Inbox Open NotificationOpen a GitHub notification URL in the browsermicrosoft/vscode-team-kit24
- Inbox Search IssuesSearch GitHub issues and PRs assigned to you, needing triage, or matching custom queriesmicrosoft/vscode-team-kit24
- Inbox SetupSet up the Inbox agent with recommended VS Code settings and gh CLI configurationmicrosoft/vscode-team-kit24
- Manage BansCreate and manage banned AST patterns that prevent specific code constructs. Use when the user wants to ban a code pattern, add a tree-sitter lint rule, or prevent specific syntax from appearing in edits.microsoft/vscode-team-kit24
- Mcp BuilderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).microsoft/copilot-sdk-samples24
- Mcp BuilderBuild MCP (Model Context Protocol) clients to connect AI agents with external tools and data sources. Use when building integrations with MCP servers.microsoft/copilot-sdk-samples24
- Monitor PrMonitor a pull request until CI status or Copilot review is available. Use when: monitor PR, watch PR, land PR, wait for CI, wait for checks, wait for review, check PR status. Starts two async terminal tasks (CI + Copilot review) and reacts when either completes.microsoft/vscode-team-kit24
- ResearchDeep research on a given topic. Use for comprehensive topic exploration — technical subjects, market analysis, architecture deep-dives, competitive analysis, etc. Also use when the user asks to 'research', 'deep dive', 'investigate', or 'find out about' a topic that requires multi-source synthesis. You should run MULTIPLE subagents in parallel to explore multiple angles and topics.microsoft/vscode-team-kit24
- Review AreasIn-depth code review that fans out parallel subagents across different review perspectives (correctness, tests, security, performance, product). It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use when the user asks for a review, PR feedback, bug hunt, or code quality check.microsoft/vscode-team-kit24
- Review PlanReview an implementation plan produced by the Plan agent. It is CRITICAL to review plans before handing off to implementation — plans often have gaps, incorrect assumptions, or suboptimal sequencing that are cheaper to catch now than after coding. Use when the user asks to 'review the plan', 'check my plan', 'is this plan ready', or after the Plan agent produces a plan.md.microsoft/vscode-team-kit24
- Rubber DuckHigh-signal feedback on plans, designs, implementations, and partial progress. Catches bugs, logic errors, and design flaws that may not be apparent to the original author. Call this skill for any non-trivial task to get a second opinion — the best time is after planning but before implementing. Call it early and often during development to course correct before problems compound. Will NOT comment on style, formatting, or trivial matters.microsoft/vscode-team-kit24
- Setup Component ExplorerSet up and integrate the Component Explorer into a vite based project.microsoft/vscode-team-kit24
- Setup Component Explorer FullFull setup of the Component Explorer including CLI, MCP server, VS Code tasks and launch config.microsoft/vscode-team-kit24
- Setup Component Explorer LightLightweight setup — install Component Explorer packages and add the Vite plugin, with MCP server for AI agent integration.microsoft/vscode-team-kit24
- Use Component ExplorerRead this skill when the project uses the component explorer and you deal with UI (fixtures, screenshots, visual testing, read when adding/changing UI).microsoft/vscode-team-kit24
- New Base ImageHow to create base image packages that bundle a VM image built from a Dockerfile. Use when creating a new distro base like quicksand-ubuntu or quicksand-alpine, scaffolding a base image, or modifying Dockerfiles for base image builds.microsoft/quicksand23
- New Overlay ImageHow to create overlay image packages that layer on top of base images. Use when creating a new overlay package like quicksand-agent, scaffolding an overlay, or modifying hatch_build.py for overlay builds.microsoft/quicksand23
- ReleaseRelease packages to GitHub via uvr. Use when user says "release", "publish packages", "cut a release", or wants to publish new package versions.microsoft/quicksand23
- App DesignUse when building or modifying the app layout, creating UI components, or making any visual design decisions. Ensures consistency, accessibility, and a polished, unique app.microsoft/fabric-apps-analytic-templates17
- App ValidationWhat to validate and how to drive Playwright for this template's app. Use alongside the playwright-cli skill — playwright-cli covers the tool's commands; this skill covers performance rules, the required validation checklist, the Fabric portal embed flow, and spec file guidance.microsoft/fabric-apps-analytic-templates17
- Dax AuthoringWrite and test DAX queries against Power BI semantic models. Covers DAX syntax rules, query patterns, time intelligence, and an iterative test workflow using the Fabric CLI query command.microsoft/fabric-apps-analytic-templates17
- Fabric CliHow to use fabric-app-data CLI to manage Fabric data source connections. Maintain workspace/item IDs in a fabric.yaml file with profiles, add connections by ID or Fabric portal URL, and generate TypeScript config for use with @microsoft/fabric-app-data.microsoft/fabric-apps-analytic-templates17